%0 Conference Proceedings
%T Evaluation of Deep Image Descriptors for Texture Retrieval
%A Bojana Gajic
%A Eduard Vazquez
%A Ramon Baldrich
%B Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017)
%D 2017
%F Bojana Gajic2017
%O CIC; 600.087
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3710), last updated on Thu, 22 Sep 2022 18:56:17 +0200
%X The increasing complexity learnt in the layers of a Convolutional Neural Network has proven to be of great help for the task of classification. The topic has received great attention in recently published literature.Nonetheless, just a handful of works study low-level representations, commonly associated with lower layers. In this paper, we explore recent findings which conclude, counterintuitively, the last layer of the VGG convolutional network is the best to describe a low-level property such as texture. To shed some light on this issue, we are proposing a psychophysical experiment to evaluate the adequacy of different layers of the VGG network for texture retrieval. Results obtained suggest that, whereas the last convolutional layer is a good choice for a specific task of classification, it might not be the best choice as a texture descriptor, showing a very poor performance on texture retrieval. Intermediate layers show the best performance, showing a good combination of basic filters, as in the primary visual cortex, and also a degree of higher level information to describe more complex textures.
%K Texture Representation
%K Texture Retrieval
%K Convolutional Neural Networks
%K Psychophysical Evaluation
%U https://pdfs.semanticscholar.org/0fb8/e49739fb3f9efd73033466af5428c59b1a3f.pdf
%P 251-257